Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.

Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

One prompt. Full delivery.

Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation

Multi-agent harness that runs Claude Code and Codex together as one system

Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.

A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.

Agenta is a workspace where you and your team build agents and automations.

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

Native-session control plane for Codex, Claude Code, OpenCode, OMP and PI. Run, resume and hand off coding sessions across your machines.

✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.